Hadoop 官方WordCount案例带你手把手的解析

浅浅的花香味﹌ 2022-12-17 02:26 149阅读 0赞

### 文章目录 ###

*   *  1.需求
     *  2.需求分析
     *  3.项目结构图
     *  4.项目依赖包
     *  5.编写Mapper
     *  6.编写Reducer
     *  7.编写Driver
     *   *  出现如下所示就欧克 ，接着看结果

## 1.需求 ##

在给定的文本文件中统计输出每一个单词出现的总次数  
**hello.txt**

hadoop hadoop
    ss ss
    cls cls
    jiao
    banzhang
    xue

## 2.需求分析 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center]

## 3.项目结构图 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center 1]

## 4.项目依赖包 ##

<dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
            <scope>compile</scope>
        </dependency>
    
    </dependencies>

## 5.编写Mapper ##

package wordcount_hdfs;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Mapper;
    
    import java.io.IOException;
    
    
    public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> { 
    
    // 0. 将创建对象的操作提取成变量，防止在 map 方法重复创建
        private Text text = new Text();
        private IntWritable i = new IntWritable(1);
    
    
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { 
            // 1. 将 Hadoop 内置的text 数据类型转换为string类型
            // 方便操作
            String string = value.toString();
    
            // 2. 对字符串进行切分
            String[] split = string.split(" ");
    
            // 3. 对字符串数组遍历，将单词映射成 （单词，1）
            for (String s : split) { 
                text.set(s);
                context.write(text, i);
            }
    
    
        }
    }

## 6.编写Reducer ##

package wordcount_hdfs;
    
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Reducer;
    
    import java.io.IOException;
    
    
    public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> { 
    
        private IntWritable total  = new IntWritable();
    
      
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { 
    
            // 定义一个 sum，用来对每个键值对的 值 做 累加操作
            int sum = 0;
    
            for (IntWritable value : values) { 
                int i = value.get();
                sum+=i;
            }
            total.set(sum);
            // 最后写出到文件
            context.write(key, total);
    
        }
    }

## 7.编写Driver ##

package wordcount_hdfs;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Job;
    import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
    import org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader;
    import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
    import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
    
    import java.io.IOException;
    
    
    public class WordCountDriver { 
    
        public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { 
    
            // 0 指定路径 这里路径有两种写法 ：
           args = new String[]{ "E:\\Hadoop\\src\\main\\resources\\input", "E:\\Hadoop\\src\\main\\resources\\ouput"};
            //args = new String[]{"E:/Hadoop/src/main/resources/", "E:/Hadoop/src/main/resources/"};
    
    // 1 获取配置信息configuration以及封装任务job
            Configuration configuration = new Configuration();
    
            Job job = Job.getInstance(configuration);
    
    // 2 设置Driver加载路径 setJarByClass
            job.setJarByClass(WordCountDriver.class);
    // 3 设置map和reduce类 setMaper setReducer
            job.setMapperClass(WordCountMapper.class);
            job.setReducerClass(WordCountReducer.class);
    // 4 设置map输出 setmapoutputkey setmapoutputvalue
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
    // 5 设置最终输出kv类型 (reducer的输出kv类型) setoutoutkey setoutputvalue
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
    // 6 设置本地的输入和输出路径 fileinputformat.setinputpath
            FileInputFormat.setInputPaths(job, new Path(args[0]));
            FileOutputFormat.setOutputPath(job, new Path(args[1]));
    
            // 7 提交
            boolean completion = job.waitForCompletion(true);
            System.exit(completion ? 0 : 1);
        }
    }

8.运行结果  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center 2]

### 出现如下所示就欧克 ，接着看结果 ###

"D:\Program Files\Java\bin\java.exe" "-javaagent:D:\office\Program Files\IntelliJ2018.2.6\lib\idea_rt.jar=53527:D:\office\Program Files\IntelliJ2018.2.6\bin" -Dfile.encoding=UTF-8 -classpath "D:\Program Files\Java\jre\lib\charsets.jar;D:\Program Files\Java\jre\lib\deploy.jar;D:\Program Files\Java\jre\lib\ext\access-bridge-64.jar;D:\Program Files\Java\jre\lib\ext\cldrdata.jar;D:\Program Files\Java\jre\lib\ext\dnsns.jar;D:\Program Files\Java\jre\lib\ext\jaccess.jar;D:\Program Files\Java\jre\lib\ext\jfxrt.jar;D:\Program Files\Java\jre\lib\ext\localedata.jar;D:\Program Files\Java\jre\lib\ext\nashorn.jar;D:\Program Files\Java\jre\lib\ext\sunec.jar;D:\Program Files\Java\jre\lib\ext\sunjce_provider.jar;D:\Program Files\Java\jre\lib\ext\sunmscapi.jar;D:\Program Files\Java\jre\lib\ext\sunpkcs11.jar;D:\Program Files\Java\jre\lib\ext\zipfs.jar;D:\Program Files\Java\jre\lib\javaws.jar;D:\Program Files\Java\jre\lib\jce.jar;D:\Program Files\Java\jre\lib\jfr.jar;D:\Program Files\Java\jre\lib\jfxswt.jar;D:\Program Files\Java\jre\lib\jsse.jar;D:\Program Files\Java\jre\lib\management-agent.jar;D:\Program Files\Java\jre\lib\plugin.jar;D:\Program Files\Java\jre\lib\resources.jar;D:\Program Files\Java\jre\lib\rt.jar;E:\Hadoop\target\classes;C:\Users\Administrator\.m2\repository\junit\junit\4.13.1\junit-4.13.1.jar;C:\Users\Administrator\.m2\repository\org\hamcrest\hamcrest-core\1.3\hamcrest-core-1.3.jar;C:\Users\Administrator\.m2\repository\org\apache\logging\log4j\log4j-core\2.8.2\log4j-core-2.8.2.jar;C:\Users\Administrator\.m2\repository\org\apache\logging\log4j\log4j-api\2.8.2\log4j-api-2.8.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-common\2.7.2\hadoop-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-annotations\2.7.2\hadoop-annotations-2.7.2.jar;D:\Program Files\Java\lib\tools.jar;C:\Users\Administrator\.m2\repository\com\google\guava\guava\11.0.2\guava-11.0.2.jar;C:\Users\Administrator\.m2\repository\commons-cli\commons-cli\1.2\commons-cli-1.2.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-math3\3.1.1\commons-math3-3.1.1.jar;C:\Users\Administrator\.m2\repository\xmlenc\xmlenc\0.52\xmlenc-0.52.jar;C:\Users\Administrator\.m2\repository\commons-httpclient\commons-httpclient\3.1\commons-httpclient-3.1.jar;C:\Users\Administrator\.m2\repository\commons-codec\commons-codec\1.4\commons-codec-1.4.jar;C:\Users\Administrator\.m2\repository\commons-io\commons-io\2.4\commons-io-2.4.jar;C:\Users\Administrator\.m2\repository\commons-net\commons-net\3.1\commons-net-3.1.jar;C:\Users\Administrator\.m2\repository\commons-collections\commons-collections\3.2.2\commons-collections-3.2.2.jar;C:\Users\Administrator\.m2\repository\javax\servlet\servlet-api\2.5\servlet-api-2.5.jar;C:\Users\Administrator\.m2\repository\org\mortbay\jetty\jetty\6.1.26\jetty-6.1.26.jar;C:\Users\Administrator\.m2\repository\org\mortbay\jetty\jetty-util\6.1.26\jetty-util-6.1.26.jar;C:\Users\Administrator\.m2\repository\javax\servlet\jsp\jsp-api\2.1\jsp-api-2.1.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-core\1.9\jersey-core-1.9.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-json\1.9\jersey-json-1.9.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jettison\jettison\1.1\jettison-1.1.jar;C:\Users\Administrator\.m2\repository\com\sun\xml\bind\jaxb-impl\2.2.3-1\jaxb-impl-2.2.3-1.jar;C:\Users\Administrator\.m2\repository\javax\xml\bind\jaxb-api\2.2.2\jaxb-api-2.2.2.jar;C:\Users\Administrator\.m2\repository\javax\xml\stream\stax-api\1.0-2\stax-api-1.0-2.jar;C:\Users\Administrator\.m2\repository\javax\activation\activation\1.1\activation-1.1.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-jaxrs\1.8.3\jackson-jaxrs-1.8.3.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-xc\1.8.3\jackson-xc-1.8.3.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-server\1.9\jersey-server-1.9.jar;C:\Users\Administrator\.m2\repository\asm\asm\3.1\asm-3.1.jar;C:\Users\Administrator\.m2\repository\commons-logging\commons-logging\1.1.3\commons-logging-1.1.3.jar;C:\Users\Administrator\.m2\repository\log4j\log4j\1.2.17\log4j-1.2.17.jar;C:\Users\Administrator\.m2\repository\net\java\dev\jets3t\jets3t\0.9.0\jets3t-0.9.0.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpclient\4.1.2\httpclient-4.1.2.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpcore\4.1.2\httpcore-4.1.2.jar;C:\Users\Administrator\.m2\repository\com\jamesmurty\utils\java-xmlbuilder\0.4\java-xmlbuilder-0.4.jar;C:\Users\Administrator\.m2\repository\commons-lang\commons-lang\2.6\commons-lang-2.6.jar;C:\Users\Administrator\.m2\repository\commons-configuration\commons-configuration\1.6\commons-configuration-1.6.jar;C:\Users\Administrator\.m2\repository\commons-digester\commons-digester\1.8\commons-digester-1.8.jar;C:\Users\Administrator\.m2\repository\commons-beanutils\commons-beanutils\1.7.0\commons-beanutils-1.7.0.jar;C:\Users\Administrator\.m2\repository\commons-beanutils\commons-beanutils-core\1.8.0\commons-beanutils-core-1.8.0.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-api\1.7.10\slf4j-api-1.7.10.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-log4j12\1.7.10\slf4j-log4j12-1.7.10.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-core-asl\1.9.13\jackson-core-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-mapper-asl\1.9.13\jackson-mapper-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\apache\avro\avro\1.7.4\avro-1.7.4.jar;C:\Users\Administrator\.m2\repository\com\thoughtworks\paranamer\paranamer\2.3\paranamer-2.3.jar;C:\Users\Administrator\.m2\repository\org\xerial\snappy\snappy-java\1.0.4.1\snappy-java-1.0.4.1.jar;C:\Users\Administrator\.m2\repository\com\google\protobuf\protobuf-java\2.5.0\protobuf-java-2.5.0.jar;C:\Users\Administrator\.m2\repository\com\google\code\gson\gson\2.2.4\gson-2.2.4.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-auth\2.7.2\hadoop-auth-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-kerberos-codec\2.0.0-M15\apacheds-kerberos-codec-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-i18n\2.0.0-M15\apacheds-i18n-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-asn1-api\1.0.0-M20\api-asn1-api-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-util\1.0.0-M20\api-util-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-framework\2.7.1\curator-framework-2.7.1.jar;C:\Users\Administrator\.m2\repository\com\jcraft\jsch\0.1.42\jsch-0.1.42.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-client\2.7.1\curator-client-2.7.1.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-recipes\2.7.1\curator-recipes-2.7.1.jar;C:\Users\Administrator\.m2\repository\com\google\code\findbugs\jsr305\3.0.0\jsr305-3.0.0.jar;C:\Users\Administrator\.m2\repository\org\apache\htrace\htrace-core\3.1.0-incubating\htrace-core-3.1.0-incubating.jar;C:\Users\Administrator\.m2\repository\org\apache\zookeeper\zookeeper\3.4.6\zookeeper-3.4.6.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-compress\1.4.1\commons-compress-1.4.1.jar;C:\Users\Administrator\.m2\repository\org\tukaani\xz\1.0\xz-1.0.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-client\2.7.2\hadoop-client-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-app\2.7.2\hadoop-mapreduce-client-app-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-common\2.7.2\hadoop-mapreduce-client-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-client\2.7.2\hadoop-yarn-client-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-server-common\2.7.2\hadoop-yarn-server-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-shuffle\2.7.2\hadoop-mapreduce-client-shuffle-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-api\2.7.2\hadoop-yarn-api-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-core\2.7.2\hadoop-mapreduce-client-core-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-common\2.7.2\hadoop-yarn-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-client\1.9\jersey-client-1.9.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-jobclient\2.7.2\hadoop-mapreduce-client-jobclient-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-hdfs\2.7.2\hadoop-hdfs-2.7.2.jar;C:\Users\Administrator\.m2\repository\commons-daemon\commons-daemon\1.0.13\commons-daemon-1.0.13.jar;C:\Users\Administrator\.m2\repository\io\netty\netty\3.6.2.Final\netty-3.6.2.Final.jar;C:\Users\Administrator\.m2\repository\io\netty\netty-all\4.0.23.Final\netty-all-4.0.23.Final.jar;C:\Users\Administrator\.m2\repository\xerces\xercesImpl\2.9.1\xercesImpl-2.9.1.jar;C:\Users\Administrator\.m2\repository\xml-apis\xml-apis\1.3.04\xml-apis-1.3.04.jar;C:\Users\Administrator\.m2\repository\org\fusesource\leveldbjni\leveldbjni-all\1.8\leveldbjni-all-1.8.jar" KVText.KVTextDriver
    2020-10-21 14:41:01,541 INFO [org.apache.hadoop.conf.Configuration.deprecation] - session.id is deprecated. Instead, use dfs.metrics.session-id
    2020-10-21 14:41:01,551 INFO [org.apache.hadoop.metrics.jvm.JvmMetrics] - Initializing JVM Metrics with processName=JobTracker, sessionId=
    2020-10-21 14:41:02,916 WARN [org.apache.hadoop.mapreduce.JobResourceUploader] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
    2020-10-21 14:41:02,936 WARN [org.apache.hadoop.mapreduce.JobResourceUploader] - No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
    2020-10-21 14:41:03,236 INFO [org.apache.hadoop.mapreduce.lib.input.FileInputFormat] - Total input paths to process : 1
    2020-10-21 14:41:03,256 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - number of splits:1
    2020-10-21 14:41:03,326 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - Submitting tokens for job: job_local297471183_0001
    2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapreduce.Job] - The url to track the job: http://localhost:8080/
    2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapreduce.Job] - Running job: job_local297471183_0001
    2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter set in config null
    2020-10-21 14:41:03,486 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
    2020-10-21 14:41:03,486 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
    2020-10-21 14:41:03,536 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for map tasks
    2020-10-21 14:41:03,536 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local297471183_0001_m_000000_0
    2020-10-21 14:41:03,566 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
    2020-10-21 14:41:03,576 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
    2020-10-21 14:41:03,616 INFO [org.apache.hadoop.mapred.Task] -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@6cec6fbe
    2020-10-21 14:41:03,626 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/E:/Hadoop/src/main/resources/input/englishconment.txt:0+80
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
    2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
    2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 
    2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
    2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
    2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 48; bufvoid = 104857600
    2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26214384(104857536); length = 13/6553600
    2020-10-21 14:41:03,796 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
    2020-10-21 14:41:03,806 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local297471183_0001_m_000000_0 is done. And is in the process of committing
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - file:/E:/Hadoop/src/main/resources/input/englishconment.txt:0+80
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local297471183_0001_m_000000_0' done.
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local297471183_0001_m_000000_0
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map task executor complete.
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for reduce tasks
    2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local297471183_0001_r_000000_0
    2020-10-21 14:41:03,836 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
    2020-10-21 14:41:03,836 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
    2020-10-21 14:41:04,115 INFO [org.apache.hadoop.mapred.Task] -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@2f6f6193
    2020-10-21 14:41:04,115 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@15648f8c
    2020-10-21 14:41:04,135 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=648858816, maxSingleShuffleLimit=162214704, mergeThreshold=428246848, ioSortFactor=10, memToMemMergeOutputsThreshold=10
    2020-10-21 14:41:04,135 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local297471183_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
    2020-10-21 14:41:04,165 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local297471183_0001_m_000000_0 decomp: 58 len: 62 to MEMORY
    2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 58 bytes from map-output for attempt_local297471183_0001_m_000000_0
    2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of size: 58, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->58
    2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
    2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
    2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
    2020-10-21 14:41:04,195 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
    2020-10-21 14:41:04,195 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total size: 47 bytes
    2020-10-21 14:41:04,205 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 58 bytes to disk to satisfy reduce memory limit
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 62 bytes from disk
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total size: 47 bytes
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
    2020-10-21 14:41:04,215 INFO [org.apache.hadoop.conf.Configuration.deprecation] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
    2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local297471183_0001_r_000000_0 is done. And is in the process of committing
    2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
    2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local297471183_0001_r_000000_0 is allowed to commit now
    2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local297471183_0001_r_000000_0' to file:/E:/Hadoop/src/main/resources/ouput/_temporary/0/task_local297471183_0001_r_000000
    2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
    2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local297471183_0001_r_000000_0' done.
    2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local297471183_0001_r_000000_0
    2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce task executor complete.
    2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local297471183_0001 running in uber mode : false
    2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] -  map 100% reduce 100%
    2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local297471183_0001 completed successfully
    2020-10-21 14:41:04,515 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 30
    	File System Counters
    		FILE: Number of bytes read=672
    		FILE: Number of bytes written=583822
    		FILE: Number of read operations=0
    		FILE: Number of large read operations=0
    		FILE: Number of write operations=0
    	Map-Reduce Framework
    		Map input records=4
    		Map output records=4
    		Map output bytes=48
    		Map output materialized bytes=62
    		Input split bytes=124
    		Combine input records=0
    		Combine output records=0
    		Reduce input groups=2
    		Reduce shuffle bytes=62
    		Reduce input records=4
    		Reduce output records=2
    		Spilled Records=8
    		Shuffled Maps =1
    		Failed Shuffles=0
    		Merged Map outputs=1
    		GC time elapsed (ms)=12
    		Total committed heap usage (bytes)=374865920
    	Shuffle Errors
    		BAD_ID=0
    		CONNECTION=0
    		IO_ERROR=0
    		WRONG_LENGTH=0
    		WRONG_MAP=0
    		WRONG_REDUCE=0
    	File Input Format Counters 
    		Bytes Read=80
    	File Output Format Counters 
    		Bytes Written=32
    
    Process finished with exit code 0

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center]: /images/20221123/81f6299f445348f8a56e4dddf30ba488.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221123/4acf7a70209b4269ba791e34bab7b9e5.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQzNjc0MzYw_size_16_color_FFFFFF_t_70_pic_center 2]: /images/20221123/500acc00c2404e9abcf40c735c2c8ca4.png